Benchmarking Open-Source Large Language Models, GPT-4 and Claude 2 on Multiple-Choice Questions in Nephrology
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
BACKGROUND In recent years, significant breakthroughs have been made in the field of natural language processing, particularly with the development of large language models (LLMs).LLMs have demonstrated remarkable capabilities on benchmarks related to general medical question answering, but there are fewer data about their performance in subspecialty fields and fewer studies still comparing the many available LLMs.These models have the potential to be used as a part of adaptive physician training, medical copilot applications, and digital patient interaction scenarios.The ability of LLMs to participate in medical training and patient care depends in part on their mastery of the knowledge content of specific medical fields. METHODSThis study investigated the medical knowledge capability of multiple LLMs in the context of their internal medicine subspecialty multiple-choice test-taking ability.We compared the performance of several open-source LLMs (Llama2-70B, Koala 7B, Falcon 7B, Stable-Vicuna 13B, and Orca-Mini 13B) with the proprietary models GPT-4 and Claude 2 on multiple-choice questions in the field of nephrology.Nephrology was chosen as an example of a conceptually complex subspecialty field in internal medicine.This study was conducted to evaluate the ability of LLMs to provide correct answers to Nephrology Self-Assessment Program (nephSAP) multiple-choice questions.These questions administered by the American Society of Nephrology help clinicians assess their knowledge in various topics in nephrology. RESULTSThe overall success of open-source LLMs in answering the 858 nephSAP multiple-choice questions correctly was 17.1 to 30.6%.In contrast, Claude 2 answered 54.4% of the questions correctly, whereas GPT-4 achieved a score of 73.3%.A dataset containing questions and ground truth labels used to assess the LLMs has been made available.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models
Liu, Y., Han, T., Ma, S., Zhang, J., Yang, Y., Tian, J., He, H., Li, A., He, M., Liu, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.01852 · Cited by 1,172
Capabilities of GPT-4 on Medical Challenge Problems
Nori, H., King, N., McKinney, S. M., Carignan, D., & Horvitz, E. (2023) · arXiv · doi:10.48550/arxiv.2303.13375 · Cited by 509
(2022) · doi:10.52202/068431-0278 · Cited by 358
Penedo, G., Malartic, Q., Hesslow, D., Cojocaru, R., Cappelli, A., Alobeidli, H., Pannier, B., Almazrouei, E., & Launay, J. (2023) · arXiv · doi:10.48550/arxiv.2306.01116 · Cited by 164
Suchman, K., Garg, S., & Trindade, A. J. (2023) · American Journal of Gastroenterology · doi:10.14309/ajg.0000000000002320 · Cited by 139
ProPILE: Probing Privacy Leakage in Large Language Models
Kim, S., Yun, S., Lee, H., Gubri, M., Yoon, S., & Oh, S. J. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-0911 · Cited by 57
Cited by
Retrieval augmented generation for large language models in healthcare: A systematic review
Amugongo, L. M., Mascheroni, P., Brooks, S., Doering, S., & Seidel, J. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000877 · Cited by 267
“For example, GPT-4 and Claude 2 have consistently outperformed their open-source counterparts in these tasks [106], illustrating the strong capabilities and potential for off-the-shelf LLMs in solving complex problems in medicine.”
Levine, D. M., Tuwani, R., Kompa, B., Varma, A., Finlayson, S. G., Mehrotra, A., & Beam, A. (2024) · The Lancet Digital Health · doi:10.1016/s2589-7500(24)00097-9 · Cited by 199
Sarstedt, M., Adler, S. J., Rau, L., & Schmitt, B. (2024) · Psychology & Marketing · doi:10.1002/mar.21982 · Cited by 149
Liu, M., Hu, W., Ding, J., Xu, J., Li, X., Zhu, L., Bai, Z., Shi, X., Wang, B., Song, H., et al. (2024) · Big Data Mining and Analytics · doi:10.26599/bdma.2024.9020044 · Cited by 41
Large language models in critical care
Biesheuvel, L. A., Workum, J. D., Reuland, M., van Genderen, M. E., Thoral, P., Dongelmans, D., & Elbers, P. (2025) · Journal of Intensive Medicine · doi:10.1016/j.jointm.2024.12.001 · Cited by 36
“[ 8 ] Similar scores have been seen in more specialized fields such as Nephrology [ 9 ] and Oncology.”
Metadata
- Authors
- Wu, S., Koo, M., Blum, L., Black, A., Kao, L., Fei, Z., Scalzo, F., & Kurtz, I.
- Venue
- NEJM AI
- Publisher
- Massachusetts Medical Society
- Published
- 2024-01-25
- Volume
- 1
- Issue
- 2
- ISSN
- 2836-9386 (ISSN-L)
- OpenAlex
- W4390943000
- Cited by
- 97
- References
- 8
- FWCI
- 7.78
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Benchmarking Open-Source Large Language Models, GPT-4 and Claude 2 on Multiple-Choice Questions in Nephrology. https://app.cochat.ai/papers/10.1056/aidbp2300092
- The paper
- Wu, S., Koo, M., Blum, L., Black, A., Kao, L., Fei, Z., Scalzo, F., & Kurtz, I. (2024). Benchmarking Open-Source Large Language Models, GPT-4 and Claude 2 on Multiple-Choice Questions in Nephrology. NEJM AI. https://doi.org/10.1056/aidbp2300092
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.